计算机应用 ›› 2020, Vol. 40 ›› Issue (4): 1023-1029.DOI: 10.11772/j.issn.1001-9081.2019081449

• 人工智能 • 上一篇    下一篇

基于特征融合的室外天气图像分类

郭志强1,2, 胡永武2, 刘鹏2, 杨杰2   

  1. 1. 宽带无线通信与传感器网络湖北重点实验室(武汉理工大学), 武汉 430070;
    2. 武汉理工大学 信息工程学院, 武汉 430070
  • 收稿日期:2019-08-29 修回日期:2019-11-13 出版日期:2020-04-10 发布日期:2019-12-09
  • 通讯作者: 胡永武
  • 作者简介:郭志强(1977-),男,湖北武汉人,副教授,博士,主要研究方向:信号处理、图像处理、模式识别、数据挖掘;胡永武(1994-),男,河南南阳人,硕士研究生,主要研究方向:图像处理、模式识别;刘鹏(1994-),男,浙江金华人,硕士研究生,主要研究方向:数据挖掘;杨杰(1960-),女,湖北武汉人,教授,博士,主要研究方向:图像分析与识别、人工智能。

Outdoor weather image classification based on feature fusion

GUO Zhiqing1,2, HU Yongwu2, LIU Peng2, YANG Jie2   

  1. 1. Hubei Key Laboratory of Broadband Wireless Communication and Sensor Networks(Wuhan University of Technology), Wuhan Hubei 430070, China;
    2. School of Information Engineering, Wuhan University of Technology, Wuhan Hubei 430070, China
  • Received:2019-08-29 Revised:2019-11-13 Online:2020-04-10 Published:2019-12-09

摘要: 天气状况对室外视频设备的成像效果有很大影响。为实现成像设备在恶劣天气下的自适应调整,从而提升智能监控系统的效果,同时针对传统的天气图像判别方法分类效果差且对相近天气现象不易分类的不足,以及深度学习方法识别天气准确率不高的问题,提出了一个将传统方法与深度学习方法相结合的特征融合模型。融合模型采用4种人工设计算法提取传统特征,采用AlexNet提取深层特征,利用融合后的特征向量进行图像天气状况的判别。融合模型在多背景数据集上的准确率达到93.90%,优于对比的3种常用方法,并且在平均精准率(AP)和平均召回率(AR)指标上也表现良好;在单背景数据集上的准确率达到96.97%,AP和AR均优于其他模型,且能很好识别特征相近的天气图像。实验结果表明提出的特征融合模型可以结合传统方法和深度学习方法的优势,提升现有天气图像分类方法的准确度,同时提高在特征相近的天气现象下的识别率。

关键词: 图像分类, 深度学习, 天气识别, 天气特征提取, 特征融合, AlexNet

Abstract: Weather conditions have great influence on the imaging performance of outdoor video equipment. In order to achieve the adaptive adjustment of imaging equipment in inclement weather,so as to improve the effect of intelligent monitoring system,by considering the characteristics that the traditional weather image classification methods have bad classification effect and cannot classify similar weather phenomena,and aiming at the low accuracy of deep learning methods on the weather recognition,a feature fusion model combining traditional methods with deep learning methods was proposed. In the fusion model,four artificially designed algorithms were used to extract traditional features,and AlexNet was used to extract deep features. The eigenvectors after fusion were used to discriminate the image weather conditions. The accuracy of the fusion model on a multi-background dataset reaches 93. 90%,which is better than those of three common methods for comparison,and also performs well on the Average Precision(AP)and Average Recall(AR)indicators;the model has the accuracy on a single background dataset reached 96. 97%,has the AP and AR better than those of other models,and can well recognize weather images with similar features. The experimental results show that the proposed feature fusion model can combine the advantages of traditional methods and deep learning methods to improve the accuracy of existing weather image classification methods,as well as improve the recognition rate under weather phenomena with similar features.

Key words: image classification, deep learning, weather recognition, weather feature extraction, feature fusion, AlexNet

中图分类号: